INDEX

Explanations

instances where something is being physically lined with something else

oai_token-act-pair · gpt-3.5-turbo

references to the action of arranging or placing items in a row or sequence

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

arb

-0.85

amaz

-0.76

 guiIcon

-0.74

ppa

-0.71

cffffcc

-0.66

abuse

-0.66

itars

-0.65

akespe

-0.65

illac

-0.63

effic

-0.63

POSITIVE LOGITS

 lining

1.13

 lined

0.93

ength

0.78

tsky

0.75

backer

0.71

umenthal

0.71

 Stevenson

0.70

 Lines

0.68

vironment

0.66

 Trout

0.65

Activations Density 0.006%

instances where something is being physically lined with something else

references to the action of arranging or placing items in a row or sequence

No Comments

No Known Activations